Abstract
Speech signal processing is a new developing discipline which has a research on the speech signal using the technology of digital signal processing. The application is very widespread. Speech coding, speech synthesis, speech recognition and speech enhancement are the primary kinds of technology of speech signal processing. In this thesis, what the author research for is just a kind of them—speech recognition.
Speech recognition is letting the computer understand our human being and react rightly. Now the mainstream of speech recognition technology is base on the basic theory of statistic mode recognition.
In this paper, firstly, the author introduces the summary of the speech signal processing, including kinds of technologies of processing, development and application. Then discuss the knowledge of speech recognition. According to the model of speech—recognition system, it describes the fundamental of every part (including pretreatment ,end point detection and template matching )such as the speech data signal process and discusses some methods of the realization. The author put the emphases on the realization of isolated speech-recognition system, discussing the principium and the methods. Finally the author simulate on the PC using MATLAB.
Key words: Endpoint Detection,Abstracting Characteristic,Dynamic Time Warping,Hidden Markov Model